Jingxi Chen

I am a PhD student in the Computer Science Department at the University of Maryland, College Park. I am working with Prof. Yiannis Aloimonos and Cornelia Fermüller at Perception and Robotics Group. I also work closely with Prof. Christopher Metzler. During my master’s study I worked with Prof. Pratap Tokekar on using Reinforcement Learning in Multi-agent System research.
My research interest lies at the intersection of computer vision, imaging, and robotics, focusing on generative models, neural representations for motion in videos, and 3D vision for robotics.

Google Scholar CV LinkedIn Email

Selected Publications (* denotes equal contribution)

Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations

Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations

Haoming Cai*, Jingxi Chen*, Brandon Y. Feng, Weiyun Jiang, Mingyang Xie, Kevin W. Zhang, Cornelia Fermüller, Yiannis Aloimonos, Ashok Veeraraghavan, Christopher A. Metzler
The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

ConVRT is an efficient INR framework for video-based turbulence mitigation that operates in test-time optimization manner

TimeRewind: Rewinding Time with Image-and-Events Video Diffusion

TimeRewind: Rewinding Time with Image-and-Events Video Diffusion

Jingxi Chen, Brandon Y. Feng, Haoming Cai, Mingyang Xie, Christopher A. Metzler, Cornelia Fermüller, Yiannis Aloimonos
Under Review, 2024

TimeRewind synthesizes the video backward into the pre-capture time with image-and-events video diffusion.

Project Page
Active Human Pose Estimation via an Autonomous UAV Agent

Active Human Pose Estimation via an Autonomous UAV Agent

Jingxi Chen, Botao He, Chahat D. Singh, Cornelia Fermüller, Yiannis Aloimonos
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

We leverage radiance fields to imagine different human views to find the best drone pose for aerial cinematography.

Project Page
Microsaccade-inspired Event Camera for Robotics

Microsaccade-inspired Event Camera for Robotics

Botao He, Ze Wang, Yuan Zhou, Jingxi Chen, Chahat D. Singh, Haojia Li, Yuman Gao, Shaojie Shen, Kaiwei Wang, Yanjun Cao, Chao Xu, Yiannis Aloimonos, Fei Gao, Cornelia Fermüller
Science Robotics, 2024

Inspired by microsaccades, we designed an event-based perception system capable of simultaneously maintaining low reaction time and stable texture.

Project Page
CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras

CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras

Sachin Shah, Matthew Chan, Haoming Cai, Jingxi Chen, Sakshum Kulshrestha, Chahat D. Singh, Christopher A. Metzler, Yiannis Aloimonos
CVPR, 2024

CodedEvents is a novel method for optimal point-spread-function engineering for 3D-tracking with event cameras.

Project Page
Proxmap: Proximal occupancy map prediction for efficient indoor robot navigation

Proxmap: Proximal occupancy map prediction for efficient indoor robot navigation

Vishnu D. Sharma, Jingxi Chen, Pratap Tokekar
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

We present a self-supervised occupancy prediction technique, ProxMaP, to predict the occupancy within the proximity of the robot to enable faster navigation.

Project Page
Multi-Agent Reinforcement Learning for Visibility-based Persistent Monitoring

Multi-Agent Reinforcement Learning for Visibility-based Persistent Monitoring

Jingxi Chen*, Amrish Baskaran*, Zhongshun Zhang, Pratap Tokekar
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

We present a Multi-Agent Reinforcement Learning (MARL) algorithm for the Visibility-based Persistent Monitoring (VPM) problem.

PDF

Template from Keunhong Park